feat(client-sagemaker): This release adds a new Neuron driver option in InferenceAmiVersion parameter for ProductionVariant. Additionally, it adds support for fetching model lifecycle status in the ListModelPackages API. Users can now use this API to view the lifecycle stage of models that have been shared with them.

awstools · awstools · commit b436013ed61e · 2025-04-18T18:12:25.000Z
diff --git a/clients/client-sagemaker/src/commands/CreateEndpointConfigCommand.ts b/clients/client-sagemaker/src/commands/CreateEndpointConfigCommand.ts
@@ -96,7 +96,7 @@ export interface CreateEndpointConfigCommandOutput extends CreateEndpointConfigO
  *       RoutingConfig: { // ProductionVariantRoutingConfig
  *         RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required
  *       },
- *       InferenceAmiVersion: "al2-ami-sagemaker-inference-gpu-2" || "al2-ami-sagemaker-inference-gpu-2-1" || "al2-ami-sagemaker-inference-gpu-3-1",
+ *       InferenceAmiVersion: "al2-ami-sagemaker-inference-gpu-2" || "al2-ami-sagemaker-inference-gpu-2-1" || "al2-ami-sagemaker-inference-gpu-3-1" || "al2-ami-sagemaker-inference-neuron-2",
  *     },
  *   ],
  *   DataCaptureConfig: { // DataCaptureConfig
@@ -209,7 +209,7 @@ export interface CreateEndpointConfigCommandOutput extends CreateEndpointConfigO
  *       RoutingConfig: {
  *         RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required
  *       },
- *       InferenceAmiVersion: "al2-ami-sagemaker-inference-gpu-2" || "al2-ami-sagemaker-inference-gpu-2-1" || "al2-ami-sagemaker-inference-gpu-3-1",
+ *       InferenceAmiVersion: "al2-ami-sagemaker-inference-gpu-2" || "al2-ami-sagemaker-inference-gpu-2-1" || "al2-ami-sagemaker-inference-gpu-3-1" || "al2-ami-sagemaker-inference-neuron-2",
  *     },
  *   ],
  *   ExecutionRoleArn: "STRING_VALUE",
diff --git a/clients/client-sagemaker/src/commands/DescribeEndpointConfigCommand.ts b/clients/client-sagemaker/src/commands/DescribeEndpointConfigCommand.ts
@@ -73,7 +73,7 @@ export interface DescribeEndpointConfigCommandOutput extends DescribeEndpointCon
  * //       RoutingConfig: { // ProductionVariantRoutingConfig
  * //         RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required
  * //       },
- * //       InferenceAmiVersion: "al2-ami-sagemaker-inference-gpu-2" || "al2-ami-sagemaker-inference-gpu-2-1" || "al2-ami-sagemaker-inference-gpu-3-1",
+ * //       InferenceAmiVersion: "al2-ami-sagemaker-inference-gpu-2" || "al2-ami-sagemaker-inference-gpu-2-1" || "al2-ami-sagemaker-inference-gpu-3-1" || "al2-ami-sagemaker-inference-neuron-2",
  * //     },
  * //   ],
  * //   DataCaptureConfig: { // DataCaptureConfig
@@ -181,7 +181,7 @@ export interface DescribeEndpointConfigCommandOutput extends DescribeEndpointCon
  * //       RoutingConfig: {
  * //         RoutingStrategy: "LEAST_OUTSTANDING_REQUESTS" || "RANDOM", // required
  * //       },
- * //       InferenceAmiVersion: "al2-ami-sagemaker-inference-gpu-2" || "al2-ami-sagemaker-inference-gpu-2-1" || "al2-ami-sagemaker-inference-gpu-3-1",
+ * //       InferenceAmiVersion: "al2-ami-sagemaker-inference-gpu-2" || "al2-ami-sagemaker-inference-gpu-2-1" || "al2-ami-sagemaker-inference-gpu-3-1" || "al2-ami-sagemaker-inference-neuron-2",
  * //     },
  * //   ],
  * //   ExecutionRoleArn: "STRING_VALUE",
diff --git a/clients/client-sagemaker/src/commands/ListModelPackagesCommand.ts b/clients/client-sagemaker/src/commands/ListModelPackagesCommand.ts
@@ -60,6 +60,11 @@ export interface ListModelPackagesCommandOutput extends ListModelPackagesOutput,
  * //       CreationTime: new Date("TIMESTAMP"), // required
  * //       ModelPackageStatus: "Pending" || "InProgress" || "Completed" || "Failed" || "Deleting", // required
  * //       ModelApprovalStatus: "Approved" || "Rejected" || "PendingManualApproval",
+ * //       ModelLifeCycle: { // ModelLifeCycle
+ * //         Stage: "STRING_VALUE", // required
+ * //         StageStatus: "STRING_VALUE", // required
+ * //         StageDescription: "STRING_VALUE",
+ * //       },
  * //     },
  * //   ],
  * //   NextToken: "STRING_VALUE",
diff --git a/clients/client-sagemaker/src/models/models_0.ts b/clients/client-sagemaker/src/models/models_0.ts
@@ -2292,7 +2292,28 @@ export interface StoppingCondition {
 
   /**
    * <p>The maximum length of time, in seconds, that a training or compilation job can be
-   *          pending before it is stopped.</p>
+   *             pending before it is stopped.</p>
+   *          <note>
+   *             <p>When working with training jobs that use capacity from <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/reserve-capacity-with-training-plans.html">training
+   *                     plans</a>, not all <code>Pending</code> job states count against the
+   *                     <code>MaxPendingTimeInSeconds</code> limit. The following scenarios do not
+   *                 increment the <code>MaxPendingTimeInSeconds</code> counter:</p>
+   *             <ul>
+   *                <li>
+   *                   <p>The plan is in a <code>Scheduled</code> state: Jobs queued (in
+   *                             <code>Pending</code> status) before a plan's start date (waiting for
+   *                         scheduled start time)</p>
+   *                </li>
+   *                <li>
+   *                   <p>Between capacity reservations: Jobs temporarily back to
+   *                             <code>Pending</code> status between two capacity reservation
+   *                         periods</p>
+   *                </li>
+   *             </ul>
+   *             <p>
+   *                <code>MaxPendingTimeInSeconds</code> only increments when jobs are actively
+   *                 waiting for capacity in an <code>Active</code> plan.</p>
+   *          </note>
    * @public
    */
   MaxPendingTimeInSeconds?: number | undefined;
diff --git a/clients/client-sagemaker/src/models/models_1.ts b/clients/client-sagemaker/src/models/models_1.ts
@@ -4455,6 +4455,7 @@ export const ProductionVariantInferenceAmiVersion = {
   AL2_GPU_2: "al2-ami-sagemaker-inference-gpu-2",
   AL2_GPU_2_1: "al2-ami-sagemaker-inference-gpu-2-1",
   AL2_GPU_3_1: "al2-ami-sagemaker-inference-gpu-3-1",
+  AL2_NEURON_2: "al2-ami-sagemaker-inference-neuron-2",
 } as const;
 
 /**
@@ -4745,6 +4746,17 @@ export interface ProductionVariant {
    *                   </li>
    *                </ul>
    *             </dd>
+   *             <dt>al2-ami-sagemaker-inference-neuron-2</dt>
+   *             <dd>
+   *                <ul>
+   *                   <li>
+   *                      <p>Accelerator: Inferentia2 and Trainium</p>
+   *                   </li>
+   *                   <li>
+   *                      <p>Neuron driver version: 2.19</p>
+   *                   </li>
+   *                </ul>
+   *             </dd>
    *          </dl>
    * @public
    */
diff --git a/clients/client-sagemaker/src/models/models_4.ts b/clients/client-sagemaker/src/models/models_4.ts
@@ -3479,6 +3479,12 @@ export interface ModelPackageSummary {
    * @public
    */
   ModelApprovalStatus?: ModelApprovalStatus | undefined;
+
+  /**
+   * <p> A structure describing the current state of the model in its life cycle. </p>
+   * @public
+   */
+  ModelLifeCycle?: ModelLifeCycle | undefined;
 }
 
 /**
diff --git a/clients/client-sagemaker/src/protocols/Aws_json1_1.ts b/clients/client-sagemaker/src/protocols/Aws_json1_1.ts
@@ -27207,6 +27207,7 @@ const de_ModelPackageSummary = (output: any, context: __SerdeContext): ModelPack
   return take(output, {
     CreationTime: (_: any) => __expectNonNull(__parseEpochTimestamp(__expectNumber(_))),
     ModelApprovalStatus: __expectString,
+    ModelLifeCycle: (_: any) => de_ModelLifeCycle(_, context),
     ModelPackageArn: __expectString,
     ModelPackageDescription: __expectString,
     ModelPackageGroupName: __expectString,
diff --git a/codegen/sdk-codegen/aws-models/sagemaker.json b/codegen/sdk-codegen/aws-models/sagemaker.json
